Login / Signup

Assessing the impact of nodule features and software algorithm on pulmonary nodule measurement uncertainty for nodules sized 20 mm or less.

Artit JirapatnakulRowena YipKyle J MyersSiyang CaiClaudia I HenschkeDavid F Yankelevitz
Published in: Quantitative imaging in medicine and surgery (2024)
Even in the best-case scenario represented in this study, using the same measurement algorithm, scanner, and scanning protocol, considerable measurement uncertainty exists in nodule volume measurement for nodules sized 20 mm or less. We found that measurement uncertainty was affected by interactions between nodule volume, algorithm, and shape complexity.
Keyphrases
  • machine learning
  • deep learning
  • randomized controlled trial
  • high resolution
  • magnetic resonance imaging
  • image quality
  • electron microscopy